© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93800
    Prev
    Next
    INDEX
    Explanations

    indefinite articles and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mazon
    -0.07
    帯
    -0.07
    ãĥŀãĥ³
    -0.07
    utenberg
    -0.06
    mony
    -0.06
    azz
    -0.06
    eson
    -0.06
    δε
    -0.06
    LETTE
    -0.06
    ekk
    -0.06
    POSITIVE LOGITS
    ç£
    0.06
     hol
    0.06
     j
    0.06
    bÃŃ
    0.06
     representation
    0.06
    756
    0.06
     ap
    0.06
     coloring
    0.06
     vert
    0.06
     representing
    0.06
    Activations Density 0.000%

    No Known Activations